© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95457
    Prev
    Next
    INDEX
    Explanations

    months and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     what
    -2.34
     had
    -2.19
     at
    -2.14
     with
    -2.11
     that
    -2.05
     if
    -1.95
     one
    -1.92
     in
    -1.89
     people
    -1.88
     some
    -1.78
    POSITIVE LOGITS
     constater
    2.05
     réjou
    1.91
     rapporter
    1.91
     corriger
    1.87
     fidé
    1.86
     récomp
    1.73
     participer
    1.70
     rempliss
    1.67
     véhic
    1.66
     prét
    1.64
    Activations Density 0.040%

    No Known Activations